About

This project implements offline speech recognition for Android using the vosk API.

Roadmap (in no particular order)

• speech input support
• multiple languages support
• multiple models for the same language (with grammars?)
• link the settings activity to the speech input settings (android system settings)
• make the app build reproducible
• (maybe) register to handle zip files and decompress the models
• (maybe) allow to delete installed models
• (maybe) add a speech IME

Contributing

This is a project I work on in my spare time, for my own use case and with my own schedule and priorities. Maintaining a community project is a hard work, that I know for having helped in doing it in the past. I am not looking forward to repeating that experience right now. This is the reason of issues and PR being closed in this repository.